> For the complete documentation index, see [llms.txt](https://yvechat.gitbook.io/wp/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://yvechat.gitbook.io/wp/resources/glossary.md). # Glossary *** #### YveChat Engine The YveChat component that runs on the user's computer at a loopback address. It discovers runtimes, executes requests, stores conversations, manages local authentication, and enforces origin policy. YveChat Engine is the mechanism that delivers sovereignty, because it keeps execution and storage on hardware the user owns. #### Hosted shell The static browser application served from the website host at `app.yvechat.xyz`. It renders the interface. It holds no models, executes no inference, and stores no conversations. The hosted shell reaches local models through a paired connection to YveChat Engine. #### Runtime Software that loads a model and produces output from it. Ollama, vLLM, and ComfyUI are runtimes. YveChat Engine discovers the runtimes installed on a machine and presents their models to the workspace. #### Ollama The primary supported local language-model runtime. It provides one installer, a model library, and model downloading. Ollama listens on `127.0.0.1:11434` by default. See [ollama.com](https://ollama.com/). #### vLLM A model serving system exposing an OpenAI-compatible HTTP interface, suited to machines with dedicated GPU infrastructure. Support in YveChat is Experimental and requires manual configuration. See [docs.vllm.ai](https://docs.vllm.ai/). #### ComfyUI The runtime used for local image generation. Image models are presented through a dynamic capability-aware image registry and appear in Image Studio, separately from language models. See [comfy.org](https://www.comfy.org/). #### Pairing The step that authorizes one hosted origin to use YveChat Engine. The user opens the local approval page, signs in locally, verifies the displayed origin, and enters a six-digit code. The resulting token binds to the approved origin, is stored as a hash locally, expires, and can be revoked. #### Loopback A network address reachable from the same computer alone, commonly `127.0.0.1` or `localhost`. YveChat Engine listens on loopback, which is why its interface is unavailable to other machines. #### Local model A model whose weights sit on the user's computer and whose inference runs on the user's hardware. A conversation with a local model reaches no external provider. It consumes the user's electricity, memory, storage, and processing time. #### Hosted provider An external service that runs models on its own infrastructure and answers requests over the internet. Full hosted-provider credential management is Planned. When a hosted provider is used, the prompt travels to that provider under its own terms. #### Sovereignty The property YveChat is built to deliver: the user holds the keys, the data, the identity, and the compute. Sovereignty is measured by what leaves the machine, and it is demonstrated through observable behavior that the user can check. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://yvechat.gitbook.io/wp/resources/glossary.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.